Deep Learning Algorithm of the SPARCC Scoring System in SI Joint MRI

Abstract

BackgroundThe Spondyloarthritis Research Consortium of Canada (SPARCC) scoring system is a sacroiliitis grading system.PurposeTo develop a deep learning‐based pipeline for grading sacroiliitis using the SPARCC scoring system.Study TypeProspective.PopulationThe study included 389 participants (42.2‐year‐old, 44.6% female, 317/35/37 for training/validation/testing). A pretrained algorithm was used to differentiate image with/without sacroiliitis.Field Strength/Sequence3‐T, short tau inversion recovery (STIR) sequence, fast spine echo.AssessmentThe regions of interest as ground truth for models' training were identified by a rheumatologist (HYC, 10‐year‐experience) and a radiologist (KHL, 6‐year‐experience) using the Assessment of Spondyloarthritis International Society definition of MRI sacroiliitis independently. Another radiologist (YYL, 4.5‐year‐experience) solved the discrepancies. The bone marrow edema (BME) and sacroiliac region models were for segmentation. Frangi‐filter detected vessels used as intense reference. Deep learning pipeline scored using SPARCC scoring system evaluating presence and features of BMEs. A rheumatologist (SCWC, 6‐year‐experience) and a radiologist (VWHL, 14‐year‐experience) scored using the SPARCC scoring system once. The radiologist (YYL) scored twice with 5‐day interval.Statistical TestsIndependent samples t‐tests and Chi‐squared tests were used. Interobserver and intraobserver reliability by intraclass correlation coefficient (ICC) and Pearson coefficient evaluated consistency between readers and the deep learning pipeline. We evaluated the performance using sensitivity, accuracy, positive predictive value, and Dice coefficient. A P‐value <0.05 was considered statistically significant.ResultsThe ICC and the Pearson coefficient between the SPARCC scores from three readers and the deep learning pipeline were 0.83 and 0.86, respectively. The sensitivity in identifying BME and accuracy of identifying SI joints and blood vessels was 0.83, 0.90, and 0.88, respectively. The dice coefficients were 0.82 (sacrum) and 0.80 (ilium).Data ConclusionThe high consistency with human readers indicated that deep learning pipeline may provide a SPARCC‐informed deep learning approach for scoring of STIR images in spondyloarthritis.Evidence Level1Technical EfficacyStage 2

Artificial intelligence and machine learning in axial spondyloarthritis

“…Bordner et al [37] and Bressem et al [38,39 && ] illustrate how artificial intelligence models accurately identify structural and inflammatory changes according to ASAS criteria, yielding comparable performance to radiologists and highlighting the importance of early detection for positive patient outcomes. Lin et al [40] successfully applied deep learning in line with the SPARCC scoring system to grade sacroiliitis on MRI, showing significant alignment with expert evaluations, and other researcher employed deep learning based models to identify, sometimes quantify BME and synovitis in axSpA patients [41][42][43]. High accuracy in BME is critical in axSpA, as early detection of inflammation alters the course of the disease.…”